CASIA OpenIR
Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders
Zhao, Jianlong1,2,3; Huang, Jinjie1; Zhi, Dongmei2,3,4; Yan, Weizheng2,3,4; Ma, Xiaohong5,6,7; Yang, Xiao5,6,7; Li, Xianbin8; Ke, Qing9; Jiang, Tianzi2,3,4,12; Calhoun, Vince D.10,11; Sui, Jing2,3,4,12
Source PublicationJOURNAL OF NEUROSCIENCE METHODS
ISSN0165-0270
2020-07-15
Volume341Pages:10
Corresponding AuthorHuang, Jinjie(jjhuang@hrbust.edu.cn) ; Sui, Jing(kittysj@gmail.com)
AbstractAs a popular deep learning method, generative adversarial networks (GAN) have achieved outstanding performance in multiple classifications and segmentation tasks. However, the application of GANs to fMRI data is relatively rare. In this work, we proposed a functional network connectivity (FNC) based GAN for classifying psychotic disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent components (ICs). The proposed GAN model consisted of one discriminator (real FNCs) and one generator (fake FNCs), each has four fully-connected layers. The generator was trained to match the discriminator in the intermediate layers while simultaneously a new objective loss was determined for the generator to improve the whole classification performance. In a case for classifying 269 major depressive disorder (MDD) patients from 286 HCs, an average accuracy of 70.1% was achieved in 10-fold cross-validation, with at least 6% higher compared to the other 6 popular classification approaches (54.5-64.2%). In another application to discriminating 558 schizophrenia patients from 542 HCs from 7 sites, the proposed GAN model achieved 80.7% accuracy in leave-one-site-out prediction, outperforming support vector machine (SVM) and deep neural net (DNN) by 3%-6%. More importantly, we are able to identify the most contributing FNC nodes and edges with the strategy of leave-one-FNC-out recursively. To the best of our knowledge, this is the first attempt to apply the GAN model on the FNC-based classification of mental disorders. Such a framework promises wide utility and great potential in neuroimaging biomarker identification.
KeywordResting-state fMRI Generative adversarial networks (GAN) Deep learning Classification Major depressive disorders Schizophrenia
DOI10.1016/j.jneumeth.2020.108756
WOS KeywordMAJOR DEPRESSIVE DISORDER ; PREFRONTAL CORTEX ; MOOD DISORDERS ; GROUP ICA ; SCHIZOPHRENIA ; FMRI ; BIPOLAR ; FRAMEWORK ; PATTERNS ; SUBJECT
Indexed BySCI
Language英语
Funding ProjectNatural Science Foundation of China[61773380] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32040100] ; Beijing Municipal Science and Technology Commission[Z181100001518005] ; National Institute of Health[R01MH117107] ; National Institute of Health[R01EB005846] ; National Institute of Health[P20GM103472] ; National Science Foundation[1539067]
Funding OrganizationNatural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Beijing Municipal Science and Technology Commission ; National Institute of Health ; National Science Foundation
WOS Research AreaBiochemistry & Molecular Biology ; Neurosciences & Neurology
WOS SubjectBiochemical Research Methods ; Neurosciences
WOS IDWOS:000546302200020
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/40057
Collection中国科学院自动化研究所
Corresponding AuthorHuang, Jinjie; Sui, Jing
Affiliation1.Harbin Univ Sci & Technol, Dept Automat, 52 Xuefu Rd, Harbin 150080, Peoples R China
2.Chinese Acad Sci, Brainnetome Ctr, Inst Automat, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
5.West China Hosp Sichuan, Psychiat Lab, State Key Lab Biotherapy, Chengdu 610041, Peoples R China
6.West China Hosp Sichuan, Mental Hlth Ctr, State Key Lab Biotherapy, Chengdu 610041, Peoples R China
7.Sichuan Univ, Huaxi Brain Res Ctr, West China Hosp, Chengdu 610041, Peoples R China
8.Capital Med Univ, Beijing Anding Hosp, Beijing Key Lab Mental Disorders, Beijing, Peoples R China
9.Zhejiang Univ, Affiliated Hosp 1, Dept Neurol, Sch Med, Hangzhou, Zhejiang, Peoples R China
10.Georgia State Univ, Triinst Ctr Translat Res Neuroimaging & Data Sci, Georgia Inst Technol, Atlanta, GA 30303 USA
11.Emory Univ, Atlanta, GA 30303 USA
12.Chinese Acad Sci, CAS Ctr Excellence Brain Sci, Inst Automat, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhao, Jianlong,Huang, Jinjie,Zhi, Dongmei,et al. Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders[J]. JOURNAL OF NEUROSCIENCE METHODS,2020,341:10.
APA Zhao, Jianlong.,Huang, Jinjie.,Zhi, Dongmei.,Yan, Weizheng.,Ma, Xiaohong.,...&Sui, Jing.(2020).Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders.JOURNAL OF NEUROSCIENCE METHODS,341,10.
MLA Zhao, Jianlong,et al."Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders".JOURNAL OF NEUROSCIENCE METHODS 341(2020):10.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Jianlong]'s Articles
[Huang, Jinjie]'s Articles
[Zhi, Dongmei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Jianlong]'s Articles
[Huang, Jinjie]'s Articles
[Zhi, Dongmei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Jianlong]'s Articles
[Huang, Jinjie]'s Articles
[Zhi, Dongmei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.